Introduction

Spotify Wrapped 2016-2020

Every december Spotify makes you a “wrapped” playlist of the 100 songs you most frequently listened to that year giving a clear picture of your music taste that year. I’ve always found that my music taste is kind of variable with a lot of different genre’s so it would be interesting to see how my music taste has changed from 2016 till now. To compare my music taste from 2016 to 2020 i will analyze my Spotify wrapped 2016-2020 playlists using the following metrics: valence, danceability, energy, tempo, key and modality.

I would also be interesting to see if a classifier can keep the playlists apart form eachother.

I expect that my music will be average in valence since i do think i listen to happy and sad songs a fairly equal amount. Furthermore i expect to ahve listened to slighty more danceable and slightly less energetic music between 2016 and 2020 due to listening more to hiphop and electronic music and less to rock and pop. I expect the tempo to be all over the place as well as the key distribution. Modality is probably in a similar fashion to valence as i think major and minor mostly define if a song is happy or sad.

In addition i’d like to analyze my most frequently listened song and one favorite song or outlier from every playlist with the use of self similarity matrices, tempo, chroma and chordograms.

Favorite/Outlier Samples:

Corpus:

My Corpus is divided into 5 groups of spotify wrapped playlists representing 2016 to 2020:

Wrapped 2016

Wrapped 2017

Wrapped 2018

Wrapped 2019

Wrapped 2020

Because I’m Happy…? (Valence Density Plot)


Multivariate Musicology (Valence, Energy, Danceability)


Wrapped Classification (KNN, Random Forests)


Time… (Tempo Histogram with Density)


Keyp on moving (Key Frequency)


And Time Again (Tempograms for Favorites/Outliers)


Acchordingly (Chordograms for Favorites/Outliers)


Feels like summer (Chromagram)


Self-Similarity Matrices


Thats A Wrap!

Valence

I expected the valence scores in my playlist to be consistently average. It appears however, that from 2016 to 2018 i started listening to happier music, after that the valence score reverted back to around 0.5 indicating that in 2019 and 2020 i mostly listened to music that’s in between happy or sad.

Danceability and Energy

My music from 2016-2020 has generally become more and more danceable every year shifting to the right until in 2020 almost all songs have a danceability higher than 0.4. My music seems to get slightly less energetic through the years. This can be explained by me listening more to hiphop and electronic music with high danceability but lower energy. It’s interesting that the correlations between the 2016 and 2018 playlists and the correlation between 2017 and 2019 are fairly similar. This indicates that regarding danceability and energy my music taste for those years had been pretty similar. 2020 was more of an odd one out as the correlation looks nothing like the others, indicationg a distinct difference in danceability and energy.

Classifiers

The classifiers had trouble distinguishing the Spotify Wrapped playlists from eachother. Probably meaning my music taste did not change that much. In 2020 however the music seemed to be distinct enough to correctly classify 50% of the playlist as coming from wrapped 2020. Songs from the 2016 and 2018 playlists kept being classified as eachother which indicates my music taste in these years must’ve been fairly similar. This is also supported by the correlation in the Danceability and Energy plot which is fairly similar in 2016 and 2018. The classifiers don’t seem to show a correlation between 2017 and 2019 as much as was apparent from the Danceability and Energy plot.

Tempo

I can conclude that i have a fairly clear preference for songs with a tempo around 100 BPM which is interesting since it doesn’t conform with Moelants(2002), suggesting that humans prefer tempi around 120-130 BPM.

Key and Modality

The key frequency is fairly distributed across all years and doesn’t change that much other than flattening out a bit in later years. As for the mode it is indeed fairly similar to how valence progressed as expected. The mode i evenly distributed between major and minor over all years except for a peak in major mode in 2018.